Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    frequent usage of functional words related to actions and prepositions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Torch
    -0.16
    otton
    -0.16
    ç©
    -0.15
     Independence
    -0.14
    ings
    -0.14
     Cotton
    -0.14
     KERNEL
    -0.13
    Kernel
    -0.13
    assen
    -0.13
    kad
    -0.13
    POSITIVE LOGITS
    osi
    0.16
    pte
    0.16
    aca
    0.15
    endon
    0.15
     Manning
    0.15
    aData
    0.14
     inc
    0.14
    že
    0.14
    /includes
    0.14
     useClass
    0.14
    Act Density 0.002%

    No Known Activations